Background: Existing methods for MRI brain tumor segmentation often suffer from excessive model parameters and suboptimal performance in delineating tumor boundaries. Methods: For this issue, a lightweight MRI brain tumor segmentation method, enhanced by hierarchical feature fusion (EHFF), is proposed. This method reduces model parameters while improving segmentation performance by integrating hierarchical features. Initially, a fine-grained feature adjustment network is crafted and guided by global contextual information, leading to the establishment of an adaptive feature learning (AFL) module. This module captures the global features of MRI brain tumor images through macro perception and micro focus, adjusting spatial granularity to enhance feature details and reduce computational complexity. Subsequently, a hierarchical feature weighting (HFW) module is constructed. This module extracts multi-scale refined features through multi-level weighting, enhancing the detailed features of spatial positions and alleviating the lack of attention to local position details in macro perception. Finally, a hierarchical feature retention (HFR) module is designed as a supplementary decoder. This module retains, up-samples, and fuses feature maps from each layer, thereby achieving better detail preservation and reconstruction. Results: Experimental results on the BraTS 2021 dataset demonstrate that the proposed method surpasses existing methods. Dice similarity coefficients (DSC) for the three semantic categories ET, TC, and WT are 88.57%, 91.53%, and 93.09%, respectively.

Existing point cloud object detection algorithms struggle to effectively capture spatial features across different scales, often resulting in inadequate responses to changes in object size and limited feature extraction capabilities, thereby affecting detection accuracy. To solve this problem, we present a point cloud object detection method based on multi-scale feature fusion of the original point cloud and projection, which aims to improve the multi-scale performance and completeness of feature extraction in point cloud object detection. First, we designed a 3D feature extraction module based on the 3D Swin Transformer. This module pre-processes the point cloud using a 3D Patch Partition approach and employs a self-attention mechanism within a 3D sliding window, along with a downsampling strategy, to effectively extract features at different scales. At the same time, we convert the 3D point cloud to a 2D image using projection technology and extract 2D features using the Swin Transformer. A 2D/3D feature fusion module is then built to integrate 2D and 3D features at the channel level through point-by-point addition and vector concatenation to improve feature completeness. Finally, the integrated feature maps are fed into the detection head to facilitate efficient object detection. Experimental results show that our method has improved the average precision of vehicle detection by 1.01% on the KITTI dataset over three levels of difficulty compared to Voxel-RCNN. In addition, visualization analyses show that our proposed algorithm also exhibits superior performance in object detection.

Point cloud compression is a pivotal technology for efficient storage and transmission of 3D point cloud data, which has significant implications for practical applications in virtual reality, autonomous driving, and cultural heritage preservation. In this paper, we propose a new learning-based model using the Retentive Network (RetNet) for point cloud compression, which achieves a lower bitrate while maintaining a high peak signal-to-noise ratio (PSNR). We first use an octree structure to segment the point cloud objects. Then, we use octree-based contextual windows to extract pivotal features from relevant sibling and ancestor nodes. Finally, we employ our proposed Octree-Retention model to effectively exploit the prior information between the spatially adjacent nodes for compression. The experimental results show that our method outperforms the state-of-the-art methods on both the LIDAR dataset(SemanticKITTI) and the object dataset(MPEG 8i), demonstrating its effectiveness.

To address the limitations in the efficiency of modality feature fusion in existing RGB-T semantic segmentation methods, which restrict segmentation performance, this paper proposes an edge-supervised attention-aware algorithm to enhance segmentation capabilities. Firstly, we design a feature fusion module incorporating channel and spatial attention mechanisms to achieve effective complementation and enhancement of RGB-T features. Secondly, we introduce an edge-aware refinement module that processes low-level modality features using global and local attention mechanisms, obtaining fine-grained feature information through element-wise multiplication. Building on this, we design a parallel structure of dilated convolutions to extract multi-scale detail information. Additionally, an EdgeHead is introduced after the edge-aware refinement module, with edge supervision applied to further enhance edge detail capture. Finally, the optimized fused features are fed into a decoder to complete the RGB-T semantic segmentation task. Experimental results demonstrate that our algorithm achieves mean Intersection over Union (mIoU) scores of 58.52% and 85.38% on the MFNet and PST900 datasets, respectively, significantly improving the accuracy of RGB-T semantic segmentation.